IMPORT

1. Librairies

library(phyloseq) # for phyloseq object
library(ggplot2)
library(ggsignif)
library(RColorBrewer)
library(cowplot)
library(plyr)
library(dplyr)
library("plotly") # plot 3D
library("microbiome") # for centered log-ratio
library("coda") # Aitchison distance
library("coda.base") # Aitchison distance
library("vegan") # NMDS
library(pheatmap) # for heatmap

2. Data

# Set path
path <- "~/Projects/IBS_Meta-analysis_16S"
path.plots <- file.path(path, "data/analysis-individual/PLOTS/plots-Nagel-EDA")

# Import phyloseq object
physeq.nagel <- readRDS(file.path(path, "phyloseq-objects/physeq_nagel.rds"))

# Sanity check
physeq.nagel
## phyloseq-class experiment-level object
## otu_table()   OTU Table:         [ 1091 taxa and 30 samples ]
## sample_data() Sample Data:       [ 30 samples by 10 sample variables ]
## tax_table()   Taxonomy Table:    [ 1091 taxa by 7 taxonomic ranks ]
## phy_tree()    Phylogenetic Tree: [ 1091 tips and 1087 internal nodes ]
## refseq()      DNAStringSet:      [ 1091 reference sequences ]

Phylogenetic tree was computed with the package phangorn, and the script was run on a cluster. Let’s check we have correctly generated a phylogenetic tree.

# Look at the tree (each dot is an ASV)
plot_tree(physeq.nagel, color = "Phylum", ladderize="left")

DEMOGRAPHICS

This dataset has covariates on gender & age. Let’s verify the distribution is similar between healthy & IBS groups.

# Number of individuals in each group
metadata <- data.frame(sample_data(physeq.nagel))
metadata %>%
  count(host_disease)
# Age
metadata %>%
  group_by(host_disease) %>%
  summarize(mean_age=mean(host_age), sd_age=sd(host_age))
wilcox.test(metadata[metadata$host_disease == "IBS", ]$host_age,
            metadata[metadata$host_disease == "Healthy", ]$host_age) # p=0.34
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  metadata[metadata$host_disease == "IBS", ]$host_age and metadata[metadata$host_disease == "Healthy", ]$host_age
## W = 136, p-value = 0.3386
## alternative hypothesis: true location shift is not equal to 0
# Gender
metadata %>%
  count(host_disease, host_sex)
chisq.test(data.frame("Female" = c(10,12),
                      "Male" = c(5,3)))
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  data.frame(Female = c(10, 12), Male = c(5, 3))
## X-squared = 0.17045, df = 1, p-value = 0.6797

ABUNDANCES

1. Absolute abundances

# Plot Phylum
plot_bar(physeq.nagel, fill = "Phylum") + facet_wrap("host_subtype", scales="free_x") +
  theme(axis.text.x = element_text(size=6, angle=90))+
  labs(x = "Samples", y = "Absolute abundance", title = "Nagel dataset (2016)")

# ggsave(file.path(path.plots, "absAbundance_phylum.jpg"), width=13, height=5)

# Plot Class
plot_bar(physeq.nagel, fill = "Class")+ facet_wrap("host_subtype", scales="free_x") +
  theme(axis.text.x = element_blank())+
  labs(x = "Samples", y = "Absolute abundance", title = "Nagel dataset (2016)")

Sequencing depth characteristics of the Nagel dataset:
- minimum of 6373 total count per sample
- median: 1.9461510^{4} total count per sample
- maximum of 2.422610^{4} total count per sample

2. Relative abundances

# Agglomerate to phylum & class levels
phylum.table <- physeq.nagel %>%
  tax_glom(taxrank = "Phylum") %>%                     # agglomerate at phylum level
  transform_sample_counts(function(x) {x/sum(x)} ) %>% # Transform to rel. abundance
  psmelt()                                             # Melt to long format

class.table <- physeq.nagel %>%
  tax_glom(taxrank = "Class") %>%
  transform_sample_counts(function(x) {x/sum(x)} ) %>%
  psmelt()


# Plot relative abundances
ggplot(phylum.table, aes(x = reorder(Sample, Sample, function(x) mean(phylum.table[Sample == x & Phylum == 'Firmicutes', 'Abundance'])),
                         y = Abundance, fill = Phylum))+
  facet_wrap(~ host_subtype, scales = "free_x") + # scales = "free" removes empty lines
  geom_bar(stat = "identity", width=0.95) +
  theme(axis.text.x = element_text(size=6, angle=90))+
  labs(x = "Samples", y = "Relative abundance", title = "Nagel dataset (2016)")

# ggsave(file.path(path.plots, "relAbundance_phylum.jpg"), width=10, height=5)

ggplot(class.table, aes(x = reorder(Sample, Sample, function(x) mean(class.table[Sample == x & Phylum == 'Firmicutes', 'Abundance'])),
                        y = Abundance, fill = Class))+
  facet_wrap(~ host_subtype, scales = "free_x") +
  geom_bar(stat = "identity", width=0.95) +
  theme(axis.text.x = element_text(size=6, angle=90))+
  labs(x = "Samples", y = "Relative abundance", title = "Nagel dataset (2016)")

# ggsave(file.path(path.plots, "relAbundance_class.jpg"), width=12, height=5)

3. Firmicutes/Bacteroidota ratio

# Extract abundance of only Bacteroidota and Firmicutes
bacter <- phylum.table %>%
  filter(Phylum == "Bacteroidota") %>%
  select(c('Sample', 'Abundance', 'host_subtype', 'host_sex', 'Phylum')) %>%
  arrange(Sample)

firmi <- phylum.table %>%
  filter(Phylum == "Firmicutes") %>%
  select(c('Sample', 'Abundance', 'host_subtype', 'host_sex', 'Phylum')) %>%
  arrange(Sample)

# Calculate log2 ratio Firmicutes/Bacteroidota
ratio.FB <- data.frame('Sample' = bacter$Sample,
                       'host_subtype' = bacter$host_subtype,
                       'Bacteroidota' = bacter$Abundance,
                       'Firmicutes' = firmi$Abundance,
                       'host_sex' = bacter$host_sex)
ratio.FB$logRatioFB <- log2(ratio.FB$Firmicutes / ratio.FB$Bacteroidota)

# Plot log2 ratio Firmicutes/Bacteroidota
ggplot(ratio.FB, aes(x = host_subtype, y = logRatioFB))+
  geom_violin(aes(fill=host_subtype))+
  scale_fill_manual(values=scales::alpha(c("blue", "red"), .3))+
  geom_jitter(width=0.1)+
  geom_signif(comparisons = list(c("HC", "IBS-D")), map_signif_level = TRUE, test="wilcox.test") +
  labs(x = "",  y = 'Log2(Firmicutes/Bacteroidota)', title = "Firmicutes:Bacteroidota ratio")+
  theme_cowplot()+
  theme(legend.position="none")

# ggsave(file.path(path.plots, "ratioFB.jpg"), width=4, height=6)

# Statistical test
wilcox.test(ratio.FB[ratio.FB$host_subtype == "IBS-D","logRatioFB"],
            ratio.FB[ratio.FB$host_subtype == "HC","logRatioFB"]) # p = 0.19
## 
##  Wilcoxon rank sum exact test
## 
## data:  ratio.FB[ratio.FB$host_subtype == "IBS-D", "logRatioFB"] and ratio.FB[ratio.FB$host_subtype == "HC", "logRatioFB"]
## W = 145, p-value = 0.1873
## alternative hypothesis: true location shift is not equal to 0

NORMALIZE DATA

# Sanity check no sample with less than 500 total count
table(sample_sums(physeq.nagel)<500) # all FALSE

#____________________________________________________________________
# PHYLOSEQ OBJECT WITH NON-ZERO COMPOSITIONS
physeq.NZcomp <- physeq.nagel
otu_table(physeq.NZcomp)[otu_table(physeq.NZcomp) == 0] <- 0.5 # pseudocounts

# Sanity check that 0 values have been replaced
# otu_table(physeq.nagel)[1:5,1:5]
# otu_table(physeq.NZcomp)[1:5,1:5]

# transform into compositions
physeq.NZcomp <- transform_sample_counts(physeq.NZcomp, function(x) x / sum(x) )
table(rowSums(otu_table(physeq.NZcomp))) # check if there is any row not summing to 1

# Save object
saveRDS(physeq.NZcomp, file.path(path, "data/analysis-individual/Nagel-2016/02_EDA-Nagel/physeq_NZcomp.rds"))

#____________________________________________________________________
# PHYLOSEQ OBJECT WITH RELATIVE COUNT (BETWEEN 0 AND 1)
physeq.rel <- physeq.nagel
physeq.rel <- transform_sample_counts(physeq.rel, function(x) x / sum(x) )

# check the counts are all relative
# otu_table(physeq.nagel)[1:5, 1:5]
# otu_table(physeq.rel)[1:5, 1:5]

# sanity check
table(rowSums(otu_table(physeq.rel))) # check if there is any row not summing to 1

# save the physeq.rel object
saveRDS(physeq.rel, file.path(path, "data/analysis-individual/Nagel-2016/02_EDA-Nagel/physeq_relative.rds"))

#____________________________________________________________________
# PHYLOSEQ OBJECT WITH COMMON-SCALE NORMALIZATION
physeq.CSN <- physeq.nagel
physeq.CSN <- transform_sample_counts(physeq.CSN, function(x) (x*min(sample_sums(physeq.CSN))) / sum(x) )

# sanity check
table(rowSums(otu_table(physeq.CSN))) # check that all rows are summing to the same total

# save the physeq.CSN object
saveRDS(physeq.CSN, file.path(path, "data/analysis-individual/Nagel-2016/02_EDA-Nagel/physeq_CSN.rds"))


#____________________________________________________________________
# PHYLOSEQ OBJECT WITH CENTERED LOG RATIO COUNT
physeq.clr <- physeq.nagel
physeq.clr <- microbiome::transform(physeq.nagel, "clr") # the function adds pseudocounts itself

# Compare the otu tables in the original phyloseq object and the new one after CLR transformation
# otu_table(physeq.nagel)[1:5, 1:5] # should contain absolute counts
# otu_table(physeq.clr)[1:5, 1:5] # should all be relative

# save the physeq.rel object
saveRDS(physeq.clr, file.path(path, "data/analysis-individual/Nagel-2016/02_EDA-Nagel/physeq_clr.rds"))

COMPUTE DISTANCES

1. UniFrac, Aitchison, Bray-Curtis and Canberra

First, let’s look at these four distances of interest.

#____________________________________________________________________________________
# Measure distances
getDistances <- function(){
  set.seed(123) # for unifrac, need to set a seed
  glom.UniF <- UniFrac(physeq.rel, weighted=TRUE, normalized=TRUE) # weighted unifrac
  glom.ait <- phyloseq::distance(physeq.clr, method = 'euclidean') # aitchison
  glom.bray <- phyloseq::distance(physeq.CSN, method = "bray") # bray-curtis
  glom.can <- phyloseq::distance(physeq.NZcomp, method = "canberra") # canberra
  dist.list <- list("UniF" = glom.UniF, "Ait" = glom.ait, "Canb" = glom.can, "Bray" = glom.bray)
  
  return(dist.list)
}


#____________________________________________________________________________________
# Plot in 2D the distances
plotDistances2D <- function(dlist, ordination="MDS"){
  plist <- NULL
  plist <- vector("list", 4)
  names(plist) <- c("Weighted Unifrac", "Aitchison", "Bray-Curtis", "Canberra")
  
  print("Unifrac")
  # Weighted UniFrac
  set.seed(123)
  iMDS.UniF <- ordinate(physeq.rel, ordination, distance=dlist$UniF)
  plist[[1]] <- plot_ordination(physeq.rel, iMDS.UniF, color="host_disease")
  
  print("Aitchison")
  # Aitchison
  set.seed(123)
  iMDS.Ait <- ordinate(physeq.clr, ordination, distance=dlist$Ait)
  plist[[2]] <- plot_ordination(physeq.clr, iMDS.Ait, color="host_disease")
  
  print("Bray")
  # Bray-Curtis
  set.seed(123)
  iMDS.Bray <- ordinate(physeq.CSN, ordination, distance=dlist$Bray)
  plist[[3]] <- plot_ordination(physeq.CSN, iMDS.Bray, color="host_disease")
  
  print("Canberra")
  # Canberra
  set.seed(123)
  iMDS.Can <- ordinate(physeq.NZcomp, ordination, distance=dlist$Can)
  plist[[4]] <- plot_ordination(physeq.NZcomp, iMDS.Can, color="host_disease")
  
  # Creating a dataframe to plot everything
  plot.df = ldply(plist, function(x) x$data)
  names(plot.df)[1] <- "distance"
  
  return(plot.df)
}

Now let’s plot!

# Get the distances & the plot data
dist.nagel <- getDistances()
plot.df <- plotDistances2D(dist.nagel)
## [1] "Unifrac"
## [1] "Aitchison"
## [1] "Bray"
## [1] "Canberra"
# Plot
ggplot(plot.df, aes(Axis.1, Axis.2, color=host_subtype))+
  geom_point(size=4, alpha=0.5)  + scale_color_manual(values = c('blue', 'red'))+
  facet_wrap(distance~., scales='free', nrow=1)+
  theme_bw()+
  theme(strip.text.x = element_text(size=20))+
  labs(color="Disease")

# ggsave(file.path(path.plots, "distances4_MDS.jpg"), height = 4, width = 15)

2. Plot in 3D

For better visualization, we will also take a glance at reduction to 3D.

#____________________________________________________________________________________
# Plot 3D ordination
plotDistances3D <- function(d, name_dist){
  
  # Reset parameters
  mds.3D <- NULL
  xyz <- NULL
  fig.3D <- NULL
  
  # Reduce distance matrix to 3 dimensions
  set.seed(123)
  mds.3D <- metaMDS(d, method="MDS", k=3, trace = 0)
  xyz <- scores(mds.3D, display="sites") # pull out the (x,y,z) coordinates
  
  # Plot
  fig.3D <- plot_ly(x=xyz[,1], y=xyz[,2], z=xyz[,3], type="scatter3d", mode="markers",
                    color=sample_data(physeq.nagel)$host_subtype, colors = c("blue", "red"))%>%
    layout(title = paste('MDS in 3D with', name_dist, 'distance', sep = ' '))
  
  return(fig.3D)
}

Now let’s plot!

plotDistances3D(dist.nagel$UniF, "UniFrac")
plotDistances3D(dist.nagel$Ait, "Aitchison")
plotDistances3D(dist.nagel$Canb, "Canberra")
plotDistances3D(dist.nagel$Bray, "Bray-Curtis")

HIERARCHICAL CLUSTERING

# For heatmaps: have group color
matcol <- data.frame(group = sample_data(physeq.nagel)[,"host_subtype"])


# Function to get heatmap from the distances computed
plotHeatmaps <- function(dlist, fontsize){
  
  # Initialize variables
  i=1
  plist <- vector("list", 4)
  names(plist) <- names(dlist)
  
  # Loop through distances
  for(d in dlist){
    plist[[i]] <- pheatmap(as.matrix(d), 
                          clustering_distance_rows = d,
                          clustering_distance_cols = d,
                          fontsize = fontsize,
                          fontsize_col = fontsize-5,
                          fontsize_row = fontsize-5,
                          annotation_col = matcol,
                          annotation_row = matcol,
                          annotation_colors = list(host_subtype = c('HC' = 'blue', 'IBS-D' = 'red')),
                          cluster_rows = T,
                          cluster_cols = T,
                          clustering_method = 'complete', # hc method
                          main = names(dlist)[i]) # have name of distance as title
    i <- i+1
  }
  
  return(plist)
}


# Get the heatmaps
heatmp.nagel <- plotHeatmaps(dlist = dist.nagel, fontsize = 8)

REPRODUCE PLOTS FROM PAPER

#___________________
# Fig 2A: PCoA on unweighted unifrac distance
set.seed(123)
pcoa <- ordinate(physeq.rel, "PCoA", distance="unifrac", weighted=FALSE)
plt.df <- merge(data.frame(pcoa$vectors), data.frame(sample_data(physeq.rel)), by="row.names")
a <- ggplot(plt.df, aes(x=Axis.1, y=Axis.2, color=host_subtype, shape=host_subtype))+
  geom_point(size=4) +
  scale_color_manual(values = c('#238b45', '#6baed6'), name="", guide="none")+
  scale_shape_manual(values = c("\u25BA", "\u25B2"), name="", guide="none")+
  theme_cowplot()
b <- ggplot(plt.df, aes(x=Axis.3, y=Axis.2, color=host_subtype, shape=host_subtype))+
  geom_point(size=4) +
  scale_color_manual(values = c('#238b45', '#6baed6'), name="", guide="none")+
  scale_shape_manual(values = c("\u25BA", "\u25B2"), name="", guide="none")+
  theme_cowplot()
c <- ggplot(plt.df, aes(x=Axis.1, y=Axis.3, color=host_subtype, shape=host_subtype))+
  geom_point(size=4) +
  scale_color_manual(values = c('#238b45', '#6baed6'), name="")+
  scale_shape_manual(values = c("\u25BA", "\u25B2"), name="")+
  theme_cowplot()

#___________________
# Fig 2B: PCoA on weighted unifrac distance
set.seed(123)
pcoa2 <- ordinate(physeq.rel, "PCoA", distance="unifrac", weighted=TRUE)
plt.df2 <- merge(data.frame(pcoa2$vectors), data.frame(sample_data(physeq.rel)), by="row.names")
d <- ggplot(plt.df2, aes(x=Axis.1, y=Axis.2, color=host_subtype, shape=host_subtype))+
  geom_point(size=4) +
  scale_color_manual(values = c('#238b45', '#6baed6'), name="", guide="none")+
  scale_shape_manual(values = c("\u25BA", "\u25B2"), name="", guide="none")+
  theme_cowplot()
e <- ggplot(plt.df2, aes(x=Axis.3, y=Axis.2, color=host_subtype, shape=host_subtype))+
  geom_point(size=4) +
  scale_color_manual(values = c('#238b45', '#6baed6'), name="", guide="none")+
  scale_shape_manual(values = c("\u25BA", "\u25B2"), name="", guide="none")+
  theme_cowplot()
f <- ggplot(plt.df2, aes(x=Axis.1, y=Axis.3, color=host_subtype, shape=host_subtype))+
  geom_point(size=4) +
  scale_color_manual(values = c('#238b45', '#6baed6'), name="")+
  scale_shape_manual(values = c("\u25BA", "\u25B2"), name="")+
  theme_cowplot()

#___________________
# PLOT all like in figure 2
ggdraw() +
  # unweighted unifrac (panel A)
  draw_grob(grob=grid::rectGrob(), x=0.005, y=0.52, width=0.99, height=.45)+
  draw_plot(a, x = 0, y = .52, width = .3, height = .45) +
  draw_plot(b, x = 0.33, y = .52, width = .3, height = .45) +
  draw_plot(c, x = 0.66, y = .52, width = .33, height = .45) +
  # weighted unifrac (panel B)
  draw_grob(grob=grid::rectGrob(), x=0.005, y=0.01, width=0.99, height=.45)+
  draw_plot(d, x = 0, y = 0, width = .3, height = .45) +
  draw_plot(e, x = 0.33, y = 0, width = .3, height = .45) +
  draw_plot(f, x = 0.66, y = 0, width = .33, height = .45) +
  draw_plot_label(label = c("A", "B"), x = 0, y = c(1, .49))